python 爬取影視網(wǎng)站下載鏈接
更新時間：2021年05月28日 10:58:51 作者：GriffinLewis2001
一個簡單的爬取影視網(wǎng)站下載鏈接的爬蟲，非常適合新手學(xué)習(xí)，感興趣的朋友可以參考下
項目地址：
https://github.com/GriffinLewis2001/Python_movie_links_scraper
運行效果
導(dǎo)入模塊
import requests,re from requests.cookies import RequestsCookieJar from fake_useragent import UserAgent import os,pickle,threading,time import concurrent.futures from goto import with_goto
爬蟲主代碼
def get_content_url_name(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="thumbnail-img" title="(.*?)"')
url_name_list=reg.findall(content)
return url_name_list
def get_content(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
return response.text
def search_durl(url):
content=get_content(url)
reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
index=reg.findall(content)[0]
download_url=url[:-5]+r'/downloadList?decriptParam='+index
content=get_content(download_url)
reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" ')
download_list=reg1.findall(content)
return download_list
def get_page(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" title="(.*?)">(.*?)<\/a>')
url_name_list=reg.findall(content)
return url_name_list
@with_goto
def main():
print("=========================================================")
name=input("請輸入劇名(輸入quit退出):")
if name == "quit":
exit()
url="http://www.yikedy.co/search?query="+name
dlist=get_page(url)
print("\n")
if(dlist):
num=0
count=0
for i in dlist:
if (name in i[1]) :
print(f"{num} {i[1]}")
num+=1
elif num==0 and count==len(dlist)-1:
goto .end
count+=1
dest=int(input("\n\n請輸入劇的編號(輸100跳過此次搜尋):"))
if dest == 100:
goto .end
x=0
print("\n以下為下載鏈接:\n")
for i in dlist:
if (name in i[1]):
if(x==dest):
for durl in search_durl(i[0]):
print(f"{durl}\n")
print("\n")
break
x+=1
else:
label .end
print("沒找到或不想看\n")
完整代碼
import requests,re
from requests.cookies import RequestsCookieJar
from fake_useragent import UserAgent
import os,pickle,threading,time
import concurrent.futures
from goto import with_goto
def get_content_url_name(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="thumbnail-img" title="(.*?)"')
url_name_list=reg.findall(content)
return url_name_list
def get_content(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
return response.text
def search_durl(url):
content=get_content(url)
reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
index=reg.findall(content)[0]
download_url=url[:-5]+r'/downloadList?decriptParam='+index
content=get_content(download_url)
reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" ')
download_list=reg1.findall(content)
return download_list
def get_page(url):
send_headers = {
"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
"Connection": "keep-alive",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8"
}
cookie_jar = RequestsCookieJar()
cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
response=requests.get(url,send_headers,cookies=cookie_jar)
response.encoding='utf-8'
content=response.text
reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" title="(.*?)">(.*?)<\/a>')
url_name_list=reg.findall(content)
return url_name_list
@with_goto
def main():
print("=========================================================")
name=input("請輸入劇名(輸入quit退出):")
if name == "quit":
exit()
url="http://www.yikedy.co/search?query="+name
dlist=get_page(url)
print("\n")
if(dlist):
num=0
count=0
for i in dlist:
if (name in i[1]) :
print(f"{num} {i[1]}")
num+=1
elif num==0 and count==len(dlist)-1:
goto .end
count+=1
dest=int(input("\n\n請輸入劇的編號(輸100跳過此次搜尋):"))
if dest == 100:
goto .end
x=0
print("\n以下為下載鏈接:\n")
for i in dlist:
if (name in i[1]):
if(x==dest):
for durl in search_durl(i[0]):
print(f"{durl}\n")
print("\n")
break
x+=1
else:
label .end
print("沒找到或不想看\n")
print("本軟件由CLY.所有\(zhòng)n\n")
while(True):
main()
以上就是python 爬取影視網(wǎng)站下載鏈接的詳細內(nèi)容，更多關(guān)于python 爬取下載鏈接的資料請關(guān)注腳本之家其它相關(guān)文章！
相關(guān)文章
下面小編就為大家分享一篇使用apidocJs快速生成在線文檔的實例講解，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧2018-02-02
Python實現(xiàn)PS圖像抽象畫風(fēng)效果的方法
這篇文章主要介紹了Python實現(xiàn)PS圖像抽象畫風(fēng)效果的方法,涉及Python基于skimage模塊進行圖像處理的相關(guān)操作技巧,需要的朋友可以參考下2018-01-01
大家好，本篇文章主要講的是用python實現(xiàn)超強的加密軟件，感興趣的同學(xué)趕快來看一看吧，對你有幫助的話記得收藏一下，方便下次瀏覽2022-01-01
python3的一個天坑問題及解決方法:報錯UnicodeDecodeError: ‘utf-8‘
在調(diào)試程序發(fā)現(xiàn)python3的一個天坑問題:報錯UnicodeDecodeError: ‘utf-8‘ codec can‘t decode byte 0xa3 in position 59: invalid,特此曝光,為眾位開發(fā)朋友提個醒2023-09-09
本文主要介紹了Scipy稀疏矩陣bsr_array的使用，文中通過示例代碼介紹的非常詳細，對大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價值，需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2023-02-02
在Python中切片(slice)是對序列型對象(如list, string, tuple)的一種高級索引方法,下面這篇文章主要給大家介紹了關(guān)于Python中切片操作的相關(guān)資料,文中通過實例代碼介紹的非常詳細,需要的朋友可以參考下2022-08-08
venv 是 Python 內(nèi)置標(biāo)準(zhǔn)庫中創(chuàng)建輕量級虛擬環(huán)境的工具,本文通過示例代碼介紹python venv和virtualenv的相關(guān)知識,感興趣的朋友跟隨小編一起看看吧2024-08-08
使用Python的Tornado框架實現(xiàn)一個Web端圖書展示頁面
Tornado是Python的一款高人氣Web開發(fā)框架,這里我們來展示使用Python的Tornado框架實現(xiàn)一個Web端圖書展示頁面的實例,通過該實例可以清楚地學(xué)習(xí)到Tornado的模板使用及整個Web程序的執(zhí)行流程.2016-07-07
今天小編就為大家分享一篇python3處理含有中文的url方法，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧2018-05-05
這篇文章主要為大家詳細介紹了如何基于Pytorch實現(xiàn)兩個分類器:?softmax分類器和感知機分類器，文中的示例代碼講解詳細，需要的可以參考一下2023-04-04